© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "call" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irth
    -0.08
     Chew
    -0.08
    els
    -0.07
    écial
    -0.07
    eson
    -0.07
    eman
    -0.07
    EMENT
    -0.07
    yalty
    -0.07
    icio
    -0.07
     druž
    -0.07
    POSITIVE LOGITS
     themselves
    0.06
    VOKE
    0.06
    bane
    0.06
    igraphy
    0.06
    458
    0.06
    IDO
    0.06
     thems
    0.06
    013
    0.05
     dorm
    0.05
    adir
    0.05
    Activations Density 0.014%

    No Known Activations